Issues · beehive-lab/GPULlama3.java · GitHub

Labels Milestones New issue

Add .claude dir with relevant skills

#119

· mikepapadim opened

on May 30, 2026

Support direct execution of K-quant GGUF weights on GPU (Q4_K, Q5_K, Q6_K)

#118

· orionpapadakis opened

on May 29, 2026

Use withCudaGraphs on PTX backend

#100

· mikepapadim opened

on Mar 11, 2026

[POC] Minimal Kernel Autotuning Support

#96

· mikepapadim opened

on Dec 22, 2025

Wrong download link for Qwen3 (1.7B) - FP16, Qwen3 (4B) - FP16 and Qwen3 (8B) - FP16

#76

· yrq0208 opened

on Nov 28, 2025

TornadoTaskRuntimeException when using Phi-3-mini-4k-instruct-fp16.gguf during TornadoVM initialization

#72

· yrq0208 opened

on Nov 25, 2025

support for llama3.2 vision

#43

· ahmedBouchaibi opened

on Aug 5, 2025

Improve error handling on out of memory exception to provide relevant solution for the llama

#31

· mikepapadim opened

on Jun 19, 2025

OutOfMemory / Misleading Hint

#30

· AdamBien opened

on Jun 19, 2025

Add pre-commit hook

good first issue

#29

· mikepapadim opened

on Jun 19, 2025

Build GUI Chatbox for GPULlama3.java Inference with embedded GPU resource monitoring

good first issue

#24

· mikepapadim opened

on Jun 13, 2025

Support for Gemma Models

#20

· mikepapadim opened

on Jun 11, 2025